© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 89664
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "coach" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ầu
    -0.08
    ISTA
    -0.07
    alist
    -0.07
    arians
    -0.07
    hed
    -0.07
    utton
    -0.07
    lust
    -0.07
    æĿĤ
    -0.07
    arian
    -0.06
    aires
    -0.06
    POSITIVE LOGITS
    (es
    0.08
     Esper
    0.07
    ella
    0.07
    istrovstvÃŃ
    0.07
    mans
    0.06
    anical
    0.06
    rylic
    0.06
    Ñĩи
    0.06
    elling
    0.06
    rain
    0.06
    Activations Density 0.016%

    No Known Activations